Medical feedback system based on sound analysis in a medical environment

Abstract

The present invention relates to a medical feedback system (100) based on sound analysis in a medical environment. With a sound scene analyzer (SSA, 10) being capable of analyzing and classifying an audio signal so as to obtain a list of one or more sound sources in the medical environment surrounding the patient, and a sound-level analyzer (SLA, 20) being capable of providing an indicator for perceived levels of corresponding sound from the list of sound sources, advanced sound analysis is possible. Finally, a sound classifier (SC, 30) is arranged for classifying said list of one or more sound sources in a medical environment with respect to a degree of avoidability, and generating a corresponding feedback signal (FEED, 50) for appropriate action by medical personal, patients and/or visitors.

The invention claimed is: 
     
       1. A medical feedback system based on sound analysis in a medical environment, the system comprising:
 a sound scene analyzer configured to:
 receive an audio signal indicative of sound near a patient in the medical environment; and 
 analyzing and classifying the audio signal to obtain a list of one or more sound sources in the medical environment surrounding the patient, 
 
 a sound-level analyzer configured to:
 receive the audio signal indicative of sound near a patient; and 
 receive said list of one or more sound sources from the sound scene analyzer; and 
 generate an indicator for perceived levels of corresponding sound from said list of sound sources, the indicator including at least one of a time window and a frequency band, and 
 
 a sound classifier configured to:
 receive said list of sound sources from the sound scene analyzer together with said indicator for perceived levels of corresponding sound from said list of sound sources from the sound-lever analyzer; 
 classify said list of one or more sound sources in a medical environment with respect to a degree of avoidability associated with the generated indicators, the degree of avoidability including an avoidability scale ranging from avoidable to unavoidable, 
 generate a corresponding feedback signal based on the degree of avoidability of each of the classified one or more sound sources; and 
 output the corresponding feedback signal to at least one feedback device. 
 
 
     
     
       2. The medical feedback system according to  claim 1 , wherein the sound scene analyzer comprises an audio feature extractor and classifier algorithm. 
     
     
       3. The medical feedback system according to  claim 2 , wherein the audio feature extractor and classifier algorithm is programmed to extract audio features representing physical, physiological, and/or psychological characteristics of the audio signal. 
     
     
       4. The medical feedback system according to  claim 3 , wherein said list comprises one of more of the following sound events or sources of sound:
 speech, including between patients, between medical personal, and between medical personal and patients, 
 alarms produced by monitoring and/or surveillance devices in the said medical environment, 
 medical equipment, 
 footsteps, 
 movements or displacements of interior building parts, such as doors, windows, ventilators, and furniture, 
 metallic objects, 
 computer related events, such as mouse and keyboard operations, 
 and/or, 
 consumer entertainment devices, such as music/video playback devices and television devices. 
 
     
     
       5. The medical feedback system according to  claim 1 , wherein the sound scene analyzer is configured to classify the audio signal according to a list of predefined sound sources representative of the medical environment. 
     
     
       6. The medical feedback system according to  claim 1 , wherein the sound scene analyzer is configured to classify audio signals based on a learning process being performed in the said medical environment. 
     
     
       7. The medical feedback system according to  claim 1 , wherein the sound-level analyzer comprises a psychoacoustic model configured to provide said indicator for perceived loudness. 
     
     
       8. The medical feedback system according to  claim 1 , wherein the sound classifier is configured to determine, based on the degree of avoidability associated with the generated indicators, whether or not a feedback signal is to be outputted from the system. 
     
     
       9. The medical feedback system according to  claim 1 , wherein the sound classifier is further configured to classify the list of sound sources with respect to the estimated annoyance of the sound sources. 
     
     
       10. The medical feedback system according to  claim 1 , wherein the feedback signal further comprises an appropriate behavioral modification signal, the behavioral modification signal corresponding to at least one of the classified sound sources; and
 control a noise source to reduce a level of noise based on the outputted feedback signal. 
 
     
     
       11. The medical feedback system according to  claim 1 , wherein the sound classifier is configured to classify said list of one or more sound sources based on a learning process being performed in the said medical environment. 
     
     
       12. The medical feedback system according to  claim 1 , wherein the sound classifier is configured to receive patient specific information from an associated patient monitoring system in the medical environment by using the said patient specific information for classification with respect to, at least, the degree of avoidability. 
     
     
       13. The medical feedback system according to  claim 1 , further including:
 a plurality of microphones configured to monitor a corresponding plurality of patients by transmitting monitored noises to at least one of the sound scene analyzer and the sound level analyzer. 
 
     
     
       14. The medical feedback system according to  claim 1 , wherein the feedback system is configured to communicate with one or more feedback devices, the feedback devices being utilizable by medical personal, visitors, and/or patients.